diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-05-04 07:50:50 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-05-04 07:50:50 -0700 |
| commit | f4622045455faaac958ca35a0cf313f3d6c14d8b (patch) | |
| tree | 96455f6f8a1afca46d939e9937913eb21782214b /arch/x86/Kconfig | |
| parent | 0a6ba092d1c8c75ae0c0617ef7f4e6f5043af311 (diff) | |
| parent | e419b4cc585680940bc42f8ca8a071d6023fb1bb (diff) | |
| download | linux-f4622045455faaac958ca35a0cf313f3d6c14d8b.tar.gz linux-f4622045455faaac958ca35a0cf313f3d6c14d8b.tar.bz2 linux-f4622045455faaac958ca35a0cf313f3d6c14d8b.zip | |
Merge branch 'fix-unmapped-word-at-a-time'
Jana Saout confirmed that this fixes the page faults he saw.
His problem was triggered by ocfs2 and autofs symlink lookups, where the
symlink allocation was at the end of a page. But the deeper reason
seems to be the use of Xen-PV, which is what then causes him to have all
these unmapped pages, which is what then makes it a problem when the
unaligned word-at-a-time code fetches data past the end of a page.
* fix-unmapped-word-at-a-time:
vfs: make word-at-a-time accesses handle a non-existing page
Diffstat (limited to 'arch/x86/Kconfig')
| -rw-r--r-- | arch/x86/Kconfig | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1d14cc6b79ad..c9866b0b77d8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -81,7 +81,7 @@ config X86 select CLKEVT_I8253 select ARCH_HAVE_NMI_SAFE_CMPXCHG select GENERIC_IOMAP - select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC + select DCACHE_WORD_ACCESS config INSTRUCTION_DECODER def_bool (KPROBES || PERF_EVENTS) |